CN116596805A - Polarization defogging method based on polarization state difference of scene object and atmosphere light - Google Patents
Polarization defogging method based on polarization state difference of scene object and atmosphere light Download PDFInfo
- Publication number
- CN116596805A CN116596805A CN202310860640.9A CN202310860640A CN116596805A CN 116596805 A CN116596805 A CN 116596805A CN 202310860640 A CN202310860640 A CN 202310860640A CN 116596805 A CN116596805 A CN 116596805A
- Authority
- CN
- China
- Prior art keywords
- polarization
- light
- atmospheric
- image
- state difference
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000010287 polarization Effects 0.000 title claims abstract description 96
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000004364 calculation method Methods 0.000 claims description 14
- 239000013598 vector Substances 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 3
- 239000011800 void material Substances 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 4
- 238000013135 deep learning Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The application belongs to the technical field of image processing, and particularly discloses a polarization defogging method based on the polarization state difference of a scene object and atmospheric light.
Description
Technical Field
The application belongs to the technical field of image processing, and particularly discloses a polarization defogging method based on the polarization state difference of a scene object and atmospheric light.
Background
In a haze weather scene, the problems of low contrast, blurred contours, lost details and the like of an image obtained by a monitoring imaging system are generally caused by the influence of factors such as scattering and reflection of suspended particles in the atmosphere. The method has great influence on the traffic of vehicles such as vehicles, ships, airplanes and the like, and on the aspects such as outdoor monitoring and the like. How to improve the image quality of a surveillance imaging system in haze climates presents a great challenge. Therefore, research on defogging technology of images is of great importance.
In the long-term development process of the defogging algorithm, three kinds of image defogging methods based on image enhancement, physical model and deep learning are sequentially presented. The image enhancement-based method has limited effect because the intrinsic cause of image degradation is not considered, and the emerging deep learning-based methods are limited by training sets, so that the robustness of the application in a real scene is still to be improved. The defogging method based on the physical model further comprises a prior single image defogging method represented by a dark channel defogging method proposed by He et al and a multi-polarization image defogging method represented by a differential polarization defogging method proposed by Schechner et al. The prior defogging method for the dark channel is an important direction of defogging of the image, but the method still has a larger lifting space in terms of defogging quality of the image, the dark channel is not suitable for all scenes, a sky area cannot be processed, meanwhile, the defogging is not clean in an area with larger fog concentration, the effect is poor, and meanwhile, the method is not suitable for monochromatic light images.
Disclosure of Invention
Based on the problems, the application provides a polarized defogging method based on the polarization state difference between a scene object and atmospheric light. The scene object and the atmosphere scattered light are separated and defogged by analyzing the polarization state difference of the scene object and the polarization state difference of the atmosphere scattered light, so that the scene object and the atmosphere light can be optimally separated, and the detection distance of a scene target in a haze environment can be better improved. The technical proposal is that,
a polarization defogging method based on the polarization state difference of a scene object and atmospheric light comprises the following steps:
s1, setting polarization angles, and sequentially collecting four groups of three channels at intervals of 45 degreesAn image or a grayscale image; calculation of an intensity map S by means of Stokes vectors 0 And polarization vector S 1 ，S 2 ；
S2, selecting a low-void area as a calculation area of polarization characteristics of a fog field, and calculating atmospheric light A at infinity ∞ Angle of polarization theta of atmospheric light A And degree of polarization p A The method comprises the steps of carrying out a first treatment on the surface of the According to S 0 ,S 1 ,S 2 ,θ A Calculating to obtain the brightest intensity image I of atmospheric light || Intensity image I with darkest atmospheric light ⊥ And a polarization diagram P;
s3, setting the included angle between the polarization direction of the object and the polarization direction of the atmospheric stray light as beta, A p Is the polarized light of the atmosphere, D p For directly transmitting the polarized light, S is used 1 ,S 2 , I || , I ⊥ Obtaining D p sin 2 Beta and A p +D p cos 2 β；
S4, defining an intensity polarization difference delta, wherein when the polarization degree of the object is greater than that of atmospheric light, the delta is greater than 0; when the polarization degree of the object is equal to that of the atmosphere, δ is equal to 0; when the polarization degree of the object is smaller than that of the atmosphere, delta is smaller than 0;
s5, the intensity map S is obtained through the polarization degree map P 0 Classifying all pixel points in the array, and calculating the atmospheric value influenced by object light;
S6, calculating a bottom envelope surface rough map of the gray level imageObtaining a bottom envelope surface fine graph A through guided filtering, wherein the bottom envelope surface fine graph A is formed by A and A ∞ Finally, the picture corresponding to the object reflected light which is not interfered by haze can be obtainedL。
Further, in step S1,
the method comprises the steps of placing a polaroid in front of a camera, obtaining four groups of three-channel images with polarization angles of 0 degree, 45 degrees, 90 degrees and 135 degrees, and converting the three-channel images into gray images; or alternatively
Real-time using short wave infrared polarizationThe acquisition device acquires gray level images I of the four angles 0 ,I 45 ,I 90 ,I 135；
S 0 ，S 1 ，S 2 The calculation steps are as follows:
;
;
。
further, in step S2,
;
;
。
further, in step S2,
;
;
。
further, in step S3, D is calculated p sin 2 Beta and A p +D p cos 2 Beta is specifically:
;
。
further, in step S4, the delta calculation step is as follows:
。
further, in step S5, the intensity map S is obtained from the polarization degree map P 0 Classifying all the pixels to obtain the atmospheric value affected by the object light,
。
Further, in step S6, a rectangular block with a size of 15×15 pixels is translated in the image, and the minimum value in the rectangular block is sequentially extracted to obtain a rough bottom envelope map。
Further, in step S6,Lthe calculation steps are as follows:
;
;
;
in the method, in the process of the application,yis the reference number of the pixel and,Ω（x) Is a local area, and x is an area label.
Further, if four sets of three-channel images are acquired in step S1, S0, S1, S2 of three components of R, G, B of the original image are respectively acquired, the three components are respectively operated by using steps S2-S6 to obtain L1, L2, L3, and finally the three components of L1, L2, L3 are combined into one picture.
Compared with the prior art, the application has the following beneficial effects:
1. according to the application, the object reflected light is separated through the difference between the object state and the atmosphere scattered light, so that a more accurate object reflected light value can be obtained.
2. And the interference of the object reflected light on the atmosphere light is further removed by solving the rough sketch of the bottom envelope surface and the fine sketch of the bottom envelope surface.
3. The polarization degree processing method provided by the application completely eliminates the atmospheric light in the processing process, determines the value range of the object reflected light and extracts the object reflected light most accurately.
Drawings
Fig. 1 is a schematic flow chart of a short-wave infrared image polarization defogging method based on polarization state difference between a scene object and atmosphere according to an embodiment of the application.
Fig. 2 is a flow chart of a method for polarized defogging of a visible light image based on a polarization state difference between a scene object and atmospheric light according to an embodiment of the present application.
FIG. 3 illustrates an atmospheric polarization angle θ using an image polarization defogging method based on a scene object and an atmospheric polarization state difference according to an embodiment of the present application A Intensity image I with brightest atmospheric light || Intensity image I with darkest atmospheric light ⊥ And the included angle between the polarization direction of the object and the polarization direction of the atmospheric stray light is beta.
FIG. 4 is an intensity graph S of an image polarization defogging method based on the polarization state difference between a scene object and the atmosphere according to an embodiment of the present application 0 Is a schematic diagram of the composition of the light intensity component.
Fig. 5 is a schematic diagram of an image processing procedure using an image polarization defogging method based on a polarization state difference between a scene object and atmospheric light according to an embodiment of the present application.
Fig. 6 is a schematic view of a scene using an image polarization defogging method based on a difference between a scene object and an atmospheric light polarization state, wherein (a) is a pre-processed image (b) is a processed image, according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which are derived by a person skilled in the art based on the embodiments of the application, fall within the scope of protection of the application.
A polarization defogging method based on the polarization state difference of a scene object and atmospheric light comprises the following steps:
s1, setting polarization angles, and sequentially collecting four groups of three-channel images or gray images at intervals of 45 degrees; calculation of an intensity map S by means of Stokes vectors 0 And polarization vector S 1 ，S 2 ；
The method comprises the steps of placing a polaroid in front of a camera, obtaining four groups of three-channel images with polarization angles of 0 degree, 45 degrees, 90 degrees and 135 degrees, and converting the three-channel images into gray images; or alternatively
Using a short wave infrared polarization real-time acquisition device to acquire gray level images I of the four angles 0 ,I 45 ,I 90 ,I 135；
S 0 ，S 1 ，S 2 The calculation steps are as follows:
;
;
。
similarly, the polarization angles can be arbitrarily set at 45 degrees intervals, such as 5 degrees, 50 degrees, 95 degrees and 140 degrees; 10 °,55 °,100 °,145 °.
S2, selecting a low-void area as a calculation area of polarization characteristics of a fog field, and calculating atmospheric light A at infinity ∞ Angle of polarization theta of atmospheric light A And degree of polarization p A The method comprises the steps of carrying out a first treatment on the surface of the According to S 0 ,S 1 ,S 2 ,θ A Calculating to obtain the brightest intensity image I of atmospheric light || Intensity image I with darkest atmospheric light ⊥ And a polarization diagram P;
;
;
;
;
;
。
s3, setting the included angle between the polarization direction of the object and the polarization direction of the atmospheric stray light as beta, A p Is the polarized light of the atmosphere, D p For directly transmitting the polarized light, S is used 1 ,S 2 , I || , I ⊥ Obtaining D p sin 2 Beta and A p +D p cos 2 β；
;
。
S4, defining an intensity polarization difference delta, wherein when the polarization degree of the object is greater than that of atmospheric light, the delta is greater than 0; when the polarization degree of the object is equal to that of the atmosphere, δ is equal to 0; when the polarization degree of the object is smaller than that of the atmosphere, delta is smaller than 0; the delta calculation steps are as follows:
。
s5, the intensity map S is obtained through the polarization degree map P 0 Classifying all pixel points in the array, and calculating the atmospheric value influenced by object light,
。
S6, calculating the bottom envelope of the image by searching the minimum value of the local area, and obtaining the atmospheric light value which is closer to the real atmospheric light value by using the minimum value of the local area as the limit approximation value of the atmospheric light of the local area. Firstly, translating a rectangular block with the size of 15 multiplied by 15 pixel points in an image in the image, sequentially extracting the minimum value in the rectangular block, and calculating to obtain a rough map of the bottom envelope surfaceThen the intensity graph is used as a guide graph, a bottom envelope surface fine graph A is obtained through a guide filtering method, the bottom envelope surface fine graph A is calculated to be regarded as the atmosphere, and finally the bottom envelope surface fine graph A is formed by A and A ∞ Can obtain the picture that does not receive object reflection light correspondence of haze interferenceL。
;
;
;
In the method, in the process of the application,ythe pixel labels, meaning that pixels are next to each other,Ω（x) As a local area of the object,xthe area labels are used to indicate that the areas are next to each other.
If four sets of three-channel images are acquired in the step S1, S0, S1 and S2 of R, G, B three components of the original image are respectively acquired, the three components are respectively operated by using the steps S2-S6, and finally the processed R, G, B three components are synthesized into a picture, namely, the obtained L1, L2 and L3 are stacked together.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. A polarization defogging method based on the polarization state difference of a scene object and atmospheric light, which is characterized by comprising the following steps:
s1, setting polarization angles, and sequentially collecting four groups of three-channel images or gray images at intervals of 45 degrees; calculation of an intensity map S by means of Stokes vectors 0 And polarization vector S 1 ，S 2 ；
S2, selecting a low-void area as a calculation area of polarization characteristics of a fog field, and calculating atmospheric light A at infinity ∞ Angle of polarization theta of atmospheric light A And degree of polarization p A The method comprises the steps of carrying out a first treatment on the surface of the According to S 0 ,S 1 ,S 2 ,θ A Calculating to obtain the brightest intensity image I of atmospheric light || Intensity image I with darkest atmospheric light ⊥ And a polarization diagram P;
s3, setting an included angle between the polarization direction of the object and the polarization direction of atmospheric stray light as beta, A p Is the polarized light of the atmosphere, D p For directly transmitting the polarized light, S is used 1 ,S 2 ,I || ,I ⊥ Obtaining D p sin 2 Beta and A p +D p cos 2 β；
S4, defining an intensity polarization difference delta, wherein when the polarization degree of the object is greater than that of atmospheric light, the delta is greater than 0; when the polarization degree of the object is equal to that of the atmosphere, δ is equal to 0; when the polarization degree of the object is smaller than that of the atmosphere, delta is smaller than 0;
s5, the intensity map S is obtained through the polarization degree map P 0 Classifying all pixel points in the array, and calculating the atmospheric value influenced by object light;
S6, calculating a bottom envelope surface rough map of the gray level imageObtaining a bottom envelope surface fine image A through guide filtering, wherein the fine image A is formed by A and A ∞ Finally, the picture corresponding to the object reflected light which is not interfered by haze can be obtainedL。
2. A polarization defogging method based on the polarization state difference of a scene object and the atmosphere according to claim 1, wherein in the step S1,
the method comprises the steps of placing a polaroid in front of a camera, obtaining four groups of three-channel images with polarization angles of 0 degree, 45 degrees, 90 degrees and 135 degrees, and converting the three-channel images into gray images; or alternatively
Using a short wave infrared polarization real-time acquisition device to acquire gray level images I of the four angles 0 ,I 45 ,I 90 ,I 135；
S 0 ，S 1 ，S 2 The calculation steps are as follows:
;
;
。
3. a polarization defogging method based on the polarization state difference of a scene object and the atmosphere according to claim 1, wherein in the step S2,
;
;
。
4. a polarization defogging method based on the polarization state difference of a scene object and the atmosphere according to claim 3, wherein in the step S2,
;
;
。
5. the method for polarization defogging based on scene objects and atmospheric light polarization state difference according to claim 1, wherein in step S3, D is calculated p sin 2 Beta and A p +D p cos 2 Beta is specifically:
，
。
6. the polarization defogging method based on the polarization state difference of a scene object and the atmosphere according to claim 1, wherein in the step S4, the delta calculation step is as follows:
。
7. the method according to claim 1, wherein in step S5, the intensity map S is obtained by using a polarization degree map P 0 Classifying all the pixels to obtain the atmospheric value affected by the object light,
。
8. The method for polarization defogging based on scene object and atmospheric light polarization state difference as claimed in claim 1, wherein in step S6, rectangular blocks with 15×15 pixel point size in the image are translated in the image, and minimum values in the rectangular blocks are sequentially extracted, so as to calculate a bottom envelope rough map。
9. A polarization defogging method based on the polarization state difference of a scene object and the atmosphere according to claim 1, wherein in step S6,Lthe calculation steps are as follows:
;
;
;
in the method, in the process of the application,yis the reference number of the pixel and,Ω（x) As a local area of the object,xare area labels.
10. The polarization defogging method based on the polarization state difference of a scene object and the atmosphere light according to claim 1, wherein if four groups of three-channel images are acquired in the step S1, S0, S1 and S2 of three components of R, G, B of an original image are respectively acquired, the three components are respectively operated by utilizing the steps S2-S6 to obtain L1, L2 and L3, and finally the three components of L1, L2 and L3 are synthesized into a picture.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310860640.9A CN116596805B (en) | 2023-07-14 | 2023-07-14 | Polarization defogging method based on polarization state difference of scene object and atmosphere light |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310860640.9A CN116596805B (en) | 2023-07-14 | 2023-07-14 | Polarization defogging method based on polarization state difference of scene object and atmosphere light |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116596805A true CN116596805A (en) | 2023-08-15 |
| CN116596805B CN116596805B (en) | 2023-09-29 |
Family
ID=87594084
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310860640.9A Active CN116596805B (en) | 2023-07-14 | 2023-07-14 | Polarization defogging method based on polarization state difference of scene object and atmosphere light |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116596805B (en) |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682443A (en) * | 2012-05-10 | 2012-09-19 | 合肥工业大学 | Rapid defogging algorithm based on polarization image guide |
| CN102930514A (en) * | 2012-09-27 | 2013-02-13 | 西安电子科技大学 | Rapid image defogging method based on atmospheric physical scattering model |
| CN105139347A (en) * | 2015-07-10 | 2015-12-09 | 中国科学院西安光学精密机械研究所 | Polarization imaging defogging method combined with dark channel prior principle |
| US9288458B1 (en) * | 2015-01-31 | 2016-03-15 | Hrl Laboratories, Llc | Fast digital image de-hazing methods for real-time video processing |
| JP2016224021A (en) * | 2015-06-03 | 2016-12-28 | 上田 智章 | Depth camera |
| CN108109113A (en) * | 2017-11-09 | 2018-06-01 | 齐鲁工业大学 | Single image to the fog method and device based on bilateral filtering and medium filtering |
| CN110278346A (en) * | 2018-03-15 | 2019-09-24 | 财团法人交大思源基金会 | Video demisting processing unit and method |
| CN111210396A (en) * | 2020-01-15 | 2020-05-29 | 北京航空航天大学 | Multispectral polarization image defogging method combined with sky light polarization model |
| US20210049744A1 (en) * | 2018-04-26 | 2021-02-18 | Chang'an University | Method for image dehazing based on adaptively improved linear global atmospheric light of dark channel |
| US20210056685A1 (en) * | 2017-12-11 | 2021-02-25 | Jiangsu University | Method and device for monitoring comprehensive growth of potted lettuce |
| CN112837233A (en) * | 2021-01-14 | 2021-05-25 | 昆明理工大学 | Polarization image defogging method for acquiring transmissivity based on differential polarization |
| CN113610728A (en) * | 2021-08-05 | 2021-11-05 | 北京信息科技大学 | Polarization double-image defogging method based on four-dark-channel mean comparison |
| KR20210143031A (en) * | 2020-05-19 | 2021-11-26 | 한국도로공사 | Method and system for removing haze in image using polarization image |
| CN114627004A (en) * | 2022-02-11 | 2022-06-14 | 南京威视科技有限公司 | Real-time polarization defogging method for atmospheric light estimation and dynamic range adjustment |
| US20220222785A1 (en) * | 2021-01-11 | 2022-07-14 | Beihang University | Image defogging method based on simulated polarization foggy scene data set |
| CN114841885A (en) * | 2022-05-10 | 2022-08-02 | 中国矿业大学(北京) | Defogging fusion processing method based on polarization image data |
| CN115187688A (en) * | 2022-07-14 | 2022-10-14 | 合肥工业大学 | Fog map reconstruction method based on atmospheric light polarization orthogonal blind separation and electronic equipment |
| CN115393216A (en) * | 2022-08-25 | 2022-11-25 | 中国人民解放军国防科技大学 | Image defogging method and device based on polarization characteristics and atmospheric transmission model |
| CN115753629A (en) * | 2022-11-25 | 2023-03-07 | 天津大海电信科技有限公司 | Method for restoring polarized video in low-visibility weather |
| CN116129222A (en) * | 2023-01-18 | 2023-05-16 | 浙江理工大学 | Target detection method based on polarization dispersion |
| EP4189635A1 (en) * | 2020-07-30 | 2023-06-07 | I2S | Method and device for underwater imaging |
-
2023
- 2023-07-14 CN CN202310860640.9A patent/CN116596805B/en active Active
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682443A (en) * | 2012-05-10 | 2012-09-19 | 合肥工业大学 | Rapid defogging algorithm based on polarization image guide |
| CN102930514A (en) * | 2012-09-27 | 2013-02-13 | 西安电子科技大学 | Rapid image defogging method based on atmospheric physical scattering model |
| US9288458B1 (en) * | 2015-01-31 | 2016-03-15 | Hrl Laboratories, Llc | Fast digital image de-hazing methods for real-time video processing |
| JP2016224021A (en) * | 2015-06-03 | 2016-12-28 | 上田 智章 | Depth camera |
| CN105139347A (en) * | 2015-07-10 | 2015-12-09 | 中国科学院西安光学精密机械研究所 | Polarization imaging defogging method combined with dark channel prior principle |
| CN108109113A (en) * | 2017-11-09 | 2018-06-01 | 齐鲁工业大学 | Single image to the fog method and device based on bilateral filtering and medium filtering |
| US20210056685A1 (en) * | 2017-12-11 | 2021-02-25 | Jiangsu University | Method and device for monitoring comprehensive growth of potted lettuce |
| CN110278346A (en) * | 2018-03-15 | 2019-09-24 | 财团法人交大思源基金会 | Video demisting processing unit and method |
| US20210049744A1 (en) * | 2018-04-26 | 2021-02-18 | Chang'an University | Method for image dehazing based on adaptively improved linear global atmospheric light of dark channel |
| CN111210396A (en) * | 2020-01-15 | 2020-05-29 | 北京航空航天大学 | Multispectral polarization image defogging method combined with sky light polarization model |
| KR20210143031A (en) * | 2020-05-19 | 2021-11-26 | 한국도로공사 | Method and system for removing haze in image using polarization image |
| EP4189635A1 (en) * | 2020-07-30 | 2023-06-07 | I2S | Method and device for underwater imaging |
| US20220222785A1 (en) * | 2021-01-11 | 2022-07-14 | Beihang University | Image defogging method based on simulated polarization foggy scene data set |
| CN112837233A (en) * | 2021-01-14 | 2021-05-25 | 昆明理工大学 | Polarization image defogging method for acquiring transmissivity based on differential polarization |
| CN113610728A (en) * | 2021-08-05 | 2021-11-05 | 北京信息科技大学 | Polarization double-image defogging method based on four-dark-channel mean comparison |
| CN114627004A (en) * | 2022-02-11 | 2022-06-14 | 南京威视科技有限公司 | Real-time polarization defogging method for atmospheric light estimation and dynamic range adjustment |
| CN114841885A (en) * | 2022-05-10 | 2022-08-02 | 中国矿业大学(北京) | Defogging fusion processing method based on polarization image data |
| CN115187688A (en) * | 2022-07-14 | 2022-10-14 | 合肥工业大学 | Fog map reconstruction method based on atmospheric light polarization orthogonal blind separation and electronic equipment |
| CN115393216A (en) * | 2022-08-25 | 2022-11-25 | 中国人民解放军国防科技大学 | Image defogging method and device based on polarization characteristics and atmospheric transmission model |
| CN115753629A (en) * | 2022-11-25 | 2023-03-07 | 天津大海电信科技有限公司 | Method for restoring polarized video in low-visibility weather |
| CN116129222A (en) * | 2023-01-18 | 2023-05-16 | 浙江理工大学 | Target detection method based on polarization dispersion |
Non-Patent Citations (4)
| Title |
|---|
| JINGJING ZHANG: "Conditional Generative Adversarial Defogging Algorithm Based on Polarization Characteristics", 2021 33RD CHINESE CONTROL AND DECISION CONFERENCE (CCDC) * |
| 夏璞;刘学斌;: "偏振光谱图像去雾技术研究", 光谱学与光谱分析, no. 08 * |
| 游江;刘鹏祖;容晓龙;李斌;徐韬祜;: "基于暗通道先验原理的偏振图像去雾增强算法研究", 激光与红外, no. 04 * |
| 王勇;薛模根;黄勤超;: "基于大气背景抑制的偏振去雾算法", 计算机工程, no. 04 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116596805B (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105279372B (en) | A kind of method and apparatus of determining depth of building | |
| Negru et al. | Exponential contrast restoration in fog conditions for driving assistance | |
| CN109993804A (en) | A kind of road scene defogging method generating confrontation network based on condition | |
| CN111965636A (en) | Night target detection method based on millimeter wave radar and vision fusion | |
| Yadav et al. | Fog removal techniques from images: A comparative review and future directions | |
| CN112016478B (en) | Complex scene recognition method and system based on multispectral image fusion | |
| CN107424133A (en) | Image defogging method, device, computer can storage medium and mobile terminals | |
| CN111709888B (en) | Aerial image defogging method based on improved generation countermeasure network | |
| CN114973028B (en) | Aerial video image real-time change detection method and system | |
| CN111144207A (en) | Human body detection and tracking method based on multi-mode information perception | |
| Bansal et al. | A review of image restoration based image defogging algorithms | |
| CN111582074A (en) | Monitoring video leaf occlusion detection method based on scene depth information perception | |
| CN103605171A (en) | All-sky imaging instrument and cloud layer characteristic analysis method based on all-sky imaging instrument | |
| Babu et al. | An efficient image dahazing using Googlenet based convolution neural networks | |
| Fu et al. | An anisotropic Gaussian filtering model for image de-hazing | |
| Yu et al. | Content-adaptive rain and snow removal algorithms for single image | |
| CN111626241A (en) | Face detection method and device | |
| CN114663352A (en) | High-precision detection method and system for defects of power transmission line and storage medium | |
| Zhao et al. | Image dehazing based on haze degree classification | |
| CN112419163A (en) | Single image weak supervision defogging method based on priori knowledge and deep learning | |
| CN103870847A (en) | Detecting method for moving object of over-the-ground monitoring under low-luminance environment | |
| CN110827375B (en) | Infrared image true color coloring method and system based on low-light-level image | |
| CN116596805B (en) | Polarization defogging method based on polarization state difference of scene object and atmosphere light | |
| CN112115737B (en) | Vehicle orientation determining method and device and vehicle-mounted terminal | |
| Maxwell et al. | Real-time physics-based removal of shadows and shading from road surfaces |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |